arXiv cs.MA· Constan\c{c}a De Herdeiro Cachim, Andrea Martin, Nicola Bastianello·· 11 小时前AI 评分20
D-GS：面向分布式超参数调优的分布式网格搜索
Distributed Grid Search for Hyperparameter Tuning
AI 导读
研究者提出分布式网格搜索（D-GS），一种基于共识的搜索方法，可在对等网络中评估并选择超参数配置，仅需能运行被调算法并计算局部梯度。其变体 D-ZGS 以更低成本提升实际表现，两者均被证明在有限时间内终止且所有智能体持有相同配置。在线性回归与逻辑回归实验中，D-GS 接近集中式参考结果，调优与部署成本仅为使用理论结果设定超参数的一小部分。
正文 · 原文
Abstract:The performance of many distributed optimization algorithms over peer-to-peer networks strongly depends on the choice of their hyperparameters. However, existing selection rules often require global quantities, yield conservative choices, or are tied to specific algorithms and hyperparameters. We propose Distributed Grid Search (D-GS), a consensus-based search method that evaluates and selects hyperparameter configurations across the network, requiring only the ability to run the tuned algorithm and evaluate local gradients. We also propose a zoom-in variant, Distributed Zoom Grid Search (D-ZGS), which improves empirical performance at a reduced cost. We prove that both methods terminate in finite time with all agents holding the same hyperparameter configuration, and quantify the (sub)optimality of this configuration. Numerical experiments on linear and logistic regression show that D-GS closely matches a centralized reference and that tuning and deployment cost a fraction of deploying algorithms with hyperparameters tuned using theoretical results.
| Subjects: | Optimization and Control (math.OC); Multiagent Systems (cs.MA) |
| Cite as: | arXiv:2610.41537 [math.OC] |
| (or arXiv:2610.41537v1 [math.OC] for this version) | |
| https://doi.org/10.48550/arXiv.2610.41537 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Nicola Bastianello [view email]
[v1]
Fri, 30 Oct 2026 10:30:27 UTC (637 KB)
来源：arXiv cs.MA · arxiv.org